Large Language Model (LLM)-based agents have demonstrated remarkable effectiveness. However, their performance can be compromised in data science scenarios that require real-time data adjustment, expertise in optimization due to complex dependencies among various tasks, and the ability to identify logical errors for precise reasoning. In this study, we introduce the Data Interpreter, a solution designed to solve with code that emphasizes three pivotal techniques to augment problem-solving in data science: 1) dynamic planning with hierarchical graph structures for real-time data adaptability;2) tool integration dynamically to enhance code proficiency during execution, enriching the requisite expertise;3) logical inconsistency identification in feedback, and efficiency enhancement through experience recording. We evaluate the Data Interpreter on various data science and real-world tasks. Compared to open-source baselines, it demonstrated superior performance, exhibiting significant improvements in machine learning tasks, increasing from 0.86 to 0.95. Additionally, it showed a 26% increase in the MATH dataset and a remarkable 112% improvement in open-ended tasks. The solution will be released at https://github.com/geekan/MetaGPT.

翻译：基于大语言模型的智能体已展现出显著效能，但在需要实时数据调整、因任务间复杂依赖而需优化专业知识、以及识别逻辑错误以实现精准推理的数据科学场景中，其性能可能受到影响。本研究提出Data Interpreter解决方案，该方案通过代码执行聚焦三项关键技术以增强数据科学问题求解能力：1）基于层级图结构的动态规划实现实时数据适应性；2）执行期间动态集成工具以增强代码熟练度，丰富所需专业知识；3）识别反馈中的逻辑不一致性，并通过经验记录提升效率。我们在多项数据科学及现实任务中评估Data Interpreter。与开源基线相比，该方案展现出更优性能：机器学习任务从0.86提升至0.95，MATH数据集提升26%，开放式任务提升达112%。该解决方案将发布于https://github.com/geekan/MetaGPT。